# Frequency-Aware Vision Transformers for High-Fidelity Super-Resolution of Earth System Models

arXiv: https://arxiv.org/abs/2502.12427 · HTML: https://mlsanity.com/paper/2502.12427/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 44 references that are in the map.
- First posted on arXiv 18 Feb 2025.

## Builds on (most cited first, 19 of 19)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Implicit Neural Representations with Periodic Activation Functions](https://mlsanity.com/paper/2006.09661/) (2020)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [On the Spectral Bias of Neural Networks](https://mlsanity.com/paper/1806.08734/) (2018)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [Accurate Image Super-Resolution Using Very Deep Convolutional Networks](https://mlsanity.com/paper/1511.04587/) (2015)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution](https://mlsanity.com/paper/1703.03126/) (2017)
- [Improving Vision Transformers by Revisiting High-frequency Components](https://mlsanity.com/paper/2204.00993/) (2022)
- [Generalised Implicit Neural Representations](https://mlsanity.com/paper/2205.15674/) (2022)
- [Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model](https://mlsanity.com/paper/2312.07112/) (2023)
- [Single Image Super-Resolution Methods: A Survey](https://mlsanity.com/paper/2202.11763/) (2022)
- [NeurOp-Diff:Continuous Remote Sensing Image Super-Resolution via Neural Operator Diffusion](https://mlsanity.com/paper/2501.09054/) (2025)
- [A Novel End-To-End Network for Reconstruction of Non-Regularly Sampled Image Data Using Locally Fully Connected Layers](https://mlsanity.com/paper/2203.09180/) (2022)

## Built on by (most cited first, 1 of 1)

- [Beyond Pointwise Error: A Multi-Metric Evaluation of Spatial Climate Downscaling](https://mlsanity.com/paper/2610.01579/) (2026)

## Abstract (arXiv)

Super-resolution can play an essential role in enhancing the spatial fidelity of Earth System Model outputs, allowing fine-scale structures highly beneficial to climate science to be recovered from coarse simulations. However, traditional deep super-resolution methods, including convolutional and transformer based models, tend to exhibit spectral bias, reconstructing low-frequency content more readily than valuable high-frequency details. In this work, we introduce ViSIR and ViFOR, two frequency-aware frameworks. ViSIR stands for the Vision Transformer-Tuned Sinusoidal Implicit Representation. ViSIR combines vision transformers with sinusoidal activations to mitigate spectral bias. ViFOR stands for the Vision Transformer Fourier Representation Network. ViFOR integrates explicit Fourier based filtering for independent low- and high-frequency learning. Evaluated on the E3SM-HR Earth system dataset across surface temperature, shortwave, and longwave fluxes, these models outperform leading Convolutional NN, Generative Networks, and vanilla transformer baselines, with ViFOR demonstrating up to 2.6~dB improvements in Peak Signal to Noise Ratio and higher Structural Similarity.